Skip to content
CaMLSysUniversity of Cambridge
Home People Publications Projects Contact

← All publications

Journey Towards Tiny Perceptual Super-Resolution

  • Royson LeeSamsung AI Center, Cambridge
  • Łukasz DudziakSamsung AI Center, Cambridge
  • Mohamed AbdelfattahSamsung AI Center, Cambridge
  • Stylianos I. VenierisSamsung AI Center, Cambridge
  • Hyeji KimSamsung AI Center, Cambridge
  • Hongkai WenSamsung AI Center, CambridgeUniversity of Warwick
  • Nicholas D. LaneSamsung AI Center, CambridgeUniversity of Cambridge

European Conference on Computer Vision (ECCV), 2020

Abstract

Recent works in single-image perceptual super-resolution (SR) have demonstrated unprecedented performance in generating realistic textures by means of deep convolutional networks. However, these convolutional models are excessively large and expensive, hindering their effective deployment to end devices. In this work, we propose a neural architecture search (NAS) approach that integrates NAS and generative adversarial networks (GANs) with recent advances in perceptual SR and pushes the efficiency of small perceptual SR models to facilitate on-device execution. Specifically, we search over the architectures of both the generator and the discriminator sequentially, highlighting the unique challenges and key observations of searching for an SR-optimized discriminator and comparing them with existing discriminator architectures in the literature. Our tiny perceptual SR (TPSR) models outperform SRGAN and EnhanceNet on both full-reference perceptual metric (LPIPS) and distortion metric (PSNR) while being up to 26.4× more memory efficient and 33.6× more compute efficient respectively.

Materials

  • PDF
BibTeX
@inproceedings{lee2020journey,
  title = {{Journey Towards Tiny Perceptual Super-Resolution}},
  author = {Lee, Royson and Dudziak, Łukasz and Abdelfattah, Mohamed and Venieris, Stylianos I. and Kim, Hyeji and Wen, Hongkai and Lane, Nicholas D.},
  year = {2020},
  booktitle = {European Conference on Computer Vision (ECCV)},
  pages = {85--102},
  publisher = {Springer International Publishing},
  doi = {10.1007/978-3-030-58574-7_6},
  url = {https://doi.org/10.1007/978-3-030-58574-7_6}
}
Cambridge Machine Learning Systems Group
Department of Computer Science and Technology
University of Cambridge
ContactGitHub